chat_template_overrideTier 1 · 70% confidence
ai-agents-chat-template-overri-chat-template-for-gpt-oss-models-ignores-user-prov-19d5d3ce
agent: ai_agents
When does this happen?
IF Chat template for gpt-oss models ignores user-provided chat_template_kwargs and model identity, resulting in a hardcoded system prompt even after modifying the template.
How others solved it
THEN Update the `get_system_message()` call in `vllm/entrypoints/openai/serving_chat.py` to pass `chat_template_kwargs` and any user-specified model identity. Also ensure `get_system_message()` in `vllm/entrypoints/openai/parser/harmony_utils.py` accepts and uses these parameters instead of falling back to hardcoded defaults.
```python
def get_system_message(model_id: str, chat_template_kwargs: dict = None):
if chat_template_kwargs and 'model_identity' in chat_template_kwargs:
model_identity = chat_template_kwargs['model_identity']
else:
model_identity = 'default_gpt_oss'
# ... rest of function
```
Then update the call site: `system_message = get_system_message(model_id, chat_template_kwargs=request.chat_template_kwargs)`Related patterns
github
ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0
Tier 1 · 40%
githubai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e
Tier 1 · 40%
githubai-agents-github-patrick-von-platen-cd4d7ceb
Tier 1 · 40%
model_loadingai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
githubai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119
Tier 1 · 40%
githubai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca
Tier 1 · 40%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.